18 July 2022 in IEEE Robotics and Automation Letters
Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image. It poses a great challenge due to its ill-posed property, which is a critical lack of depth information in the 2D image plane. While existing approaches leverage off-the-shelf depth estimation or rely on LiDAR sensors to mitigate this problem, dependence on the additional depth model or expensive equipment severely limits their scalability to generic 3D perception. In this paper, we propose a stereo-guided monocular 3D object detection framework, dubbed SGM3D, which aligns the monocular feature to the stereo feature and exploits the network's ability of generating the cross-modal feature for accurate 3D object detection. We present a multi-granularity feature alignment (MG-FA) mechanism to exploit the network's ability to generate stereo-mimicking features given only monocular cues. Coarse feature-level, as well as fine anchor-level feature alignment, are both leveraged for monocular feature guidance. In addition, we introduce an IoU matching-based feature alignment (IoU-MA) method for object-level feature alignment between the stereo and monocular predictions to alleviate the mismatches while adopting the MG-FA. Extensive experiments on the KITTI datasets demonstrate the effectiveness of our method. Code is publicly available at https://github.com/zhouzheyuan/sgm3d .
21 September 2017 in IEEE Access
Stereo matching is a challenging problem with respect to weak texture, discontinuities, illumination difference and occlusions. Therefore, a deep learning framework is presented in this paper, which focuses on the first and last stage of typical stereo methods: the matching cost computation and the disparity refinement. For matching cost computation, two patch-based network architectures are exploited to allow the trade-off between speed and accuracy, both of which leverage multi-size and multi-layer pooling unit with no strides to learn cross-scale feature representations. For disparity refinement, unlike traditional handcrafted refinement algorithms, we incorporate the initial optimal and sub-optimal disparity maps before outlier detection. Furthermore, diverse base learners are encouraged to focus on specific replacement tasks, corresponding to the smooth regions and details. Experiments on different datasets demonstrate the effectiveness of our approach, which is able to obtain sub-pixel accuracy and restore occlusions to a great extent. Specifically, our accurate framework attains near-peak accuracy both in non-occluded and occluded region and our fast framework achieves competitive performance against the fast algorithms on Middlebury benchmark.